Use of Linguistic Information of Accent Phrases for Automatic Extraction of F0 Contour Generation Process Model Parameters

A method was developed to utilize linguistic information (lexical accent types and syntactic boundaries) to improve the performance of the automatic extraction of the F0 contour generation process model commands. The extraction scheme is first to smooth the observed F0 contour by a piecewise 3 order polynomial function and to locate accent command positions by taking the derivative of the function. The phrase commands are estimated from the residual F0 contour, which is obtained by subtracting the extracted accent components from the observed F0 contour. If the results of automatic extraction differ from those estimated from the linguistic information, they are modified according to the several rules. The results showed that some errors could be corrected by the use of linguistic information; especially when the initial word of an accent phrase is type 0 accent. As a whole, the correct extraction rate (recall rate) was increased from 79.8 % to 82.3 % for phrase commands and from 81.6 % to 85.9 % for accent commands.